Checkpoint step: 100 | Target words: 1,000,000 | Actual tokens: 1,638,400 | Actual words: 1,001,562.4374023477 | Progress: 1/28
Browse files- config.json +33 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MambaForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"conv_kernel": 4,
|
7 |
+
"eos_token_id": 0,
|
8 |
+
"expand": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.1,
|
12 |
+
"intermediate_size": 1536,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "mamba",
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"rescale_prenorm_residual": false,
|
18 |
+
"residual_in_fp32": true,
|
19 |
+
"state_size": 16,
|
20 |
+
"time_step_floor": 0.0001,
|
21 |
+
"time_step_init_scheme": "random",
|
22 |
+
"time_step_max": 0.1,
|
23 |
+
"time_step_min": 0.001,
|
24 |
+
"time_step_rank": 48,
|
25 |
+
"time_step_scale": 1.0,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.51.3",
|
28 |
+
"use_bias": false,
|
29 |
+
"use_cache": true,
|
30 |
+
"use_conv_bias": true,
|
31 |
+
"use_mambapy": false,
|
32 |
+
"vocab_size": 50257
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aea26f417914bf9581f9a8c7b12cb0933d0f21c604dde736f497b869db1faf26
|
3 |
+
size 637198304
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:949043c89677afbc1ca58c11736f8539988b431d0cd06b3fa4dd8e03739a2743
|
3 |
+
size 5841
|